ETR is looking for a data scientist with a passion for the NBA — preferably someone who has analyzed the game through a fantasy sports and/or sports betting lens. This role will be focused on planning and executing improvements to our basketball projection system. At the highest level, this means you will help us improve our existing methodology for predicting how basketball players will perform in a given game. Other details:
- Location: This role is fully remote.
- Duration: The expectation is that this role will be contained to a ~6 month project. We expect the workload to be significant during this period (at least 15 hours per week, on average), but there is no specific expectation for what times/days you need to be available. We can work around prior commitments and/or unique situations for exceptional candidates, should they exist.
- After this project ends, there is potential for an ongoing role at ETR depending on the candidate’s performance, availability, and skills.
- Compensation: TBD depending on a candidate’s skill and availability.
Beyond availability and agreeing on compensation, candidates must meet the following criteria: (a) be self-motivated, (b) able to work cooperatively with the broader ETR team, (c) have significant experience in data science/data analysis, and (d) have significant experience analyzing basketball. We don’t expect candidates to have perfect knowledge in every aspect of (c) and (d), but they should know enough to work sufficiently on their own rather than needing extensive training. While ETR will provide support, candidates will be expected to execute the majority of this project on their own.
In addition to the above, preference will be given to candidates who have:
- Familiarity with ETR
- Extensive coding experience in both Python and R
- Substantial basketball and/or NBA knowledge (and can demonstrate a history of putting that interest to use in fantasy sports, gambling, prediction, etc.)
- Strong fluency working with AI products (with examples of previous projects/uses)
- Experience collecting data from scratch (e.g., scraping from web pages, gathering from APIs). Even better if this is NBA data.
- Experience organizing/aggregating data
- Experience with AWS, GitHub, and Terraform
- Experience working in the sports domain
To apply, please send your résumé, a very brief introduction of yourself and familiarity with ETR, a description of how you meet the above criteria, and a comprehensive answer (including code) to at least one of the questions below to [email protected]:
- How should team/player projected playing time (i.e., minutes played) change as a function of availability (e.g., injuries, Q-tags, minutes restrictions)?
- How should multiple sets of team playing time projections be combined probabilistically to arrive at a final projection? For example, given one set of LAL projections with LeBron OUT and one set with LeBron IN, how should those two sets be combined to determine the final projections for LAL?
- For a given NBA game, how should we expect box-score stats to correlate between players (both teammates and opponents)?
- How do NBA per-possession efficiency stats change as a function of the expected score of a game (e.g., how should projected player usage change if their team is heavily favored in a game)?
